#include <asm/tlbflush.h>
#include <linux/swapops.h>
-DEFINE_SPINLOCK(swaplock);
+DEFINE_SPINLOCK(swap_lock);
unsigned int nr_swapfiles;
long total_swap_pages;
static int swap_overflow;
/*
* We need this because the bdev->unplug_fn can sleep and we cannot
- * hold swap_list_lock while calling the unplug_fn. And swap_list_lock
+ * hold swap_lock while calling the unplug_fn. And swap_lock
* cannot be turned into a semaphore.
*/
static DECLARE_RWSEM(swap_unplug_sem);
-#define SWAPFILE_CLUSTER 256
-
void swap_unplug_io_fn(struct backing_dev_info *unused_bdi, struct page *page)
{
swp_entry_t entry;
down_read(&swap_unplug_sem);
- entry.val = page->private;
+ entry.val = page_private(page);
if (PageSwapCache(page)) {
struct block_device *bdev = swap_info[swp_type(entry)].bdev;
struct backing_dev_info *bdi;
/*
* If the page is removed from swapcache from under us (with a
* racy try_to_unuse/swapoff) we need an additional reference
- * count to avoid reading garbage from page->private above. If
- * the WARN_ON triggers during a swapoff it maybe the race
+ * count to avoid reading garbage from page_private(page) above.
+ * If the WARN_ON triggers during a swapoff it maybe the race
* condition and it's harmless. However if it triggers without
* swapoff it signals a problem.
*/
up_read(&swap_unplug_sem);
}
+#define SWAPFILE_CLUSTER 256
+#define LATENCY_LIMIT 256
+
static inline unsigned long scan_swap_map(struct swap_info_struct *si)
{
- unsigned long offset;
+ unsigned long offset, last_in_cluster;
+ int latency_ration = LATENCY_LIMIT;
+
/*
- * We try to cluster swap pages by allocating them
- * sequentially in swap. Once we've allocated
- * SWAPFILE_CLUSTER pages this way, however, we resort to
- * first-free allocation, starting a new cluster. This
- * prevents us from scattering swap pages all over the entire
- * swap partition, so that we reduce overall disk seek times
- * between swap pages. -- sct */
- if (si->cluster_nr) {
- while (si->cluster_next <= si->highest_bit) {
- offset = si->cluster_next++;
+ * We try to cluster swap pages by allocating them sequentially
+ * in swap. Once we've allocated SWAPFILE_CLUSTER pages this
+ * way, however, we resort to first-free allocation, starting
+ * a new cluster. This prevents us from scattering swap pages
+ * all over the entire swap partition, so that we reduce
+ * overall disk seek times between swap pages. -- sct
+ * But we do now try to find an empty cluster. -Andrea
+ */
+
+ si->flags += SWP_SCANNING;
+ if (unlikely(!si->cluster_nr)) {
+ si->cluster_nr = SWAPFILE_CLUSTER - 1;
+ if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER)
+ goto lowest;
+ spin_unlock(&swap_lock);
+
+ offset = si->lowest_bit;
+ last_in_cluster = offset + SWAPFILE_CLUSTER - 1;
+
+ /* Locate the first empty (unaligned) cluster */
+ for (; last_in_cluster <= si->highest_bit; offset++) {
if (si->swap_map[offset])
- continue;
- si->cluster_nr--;
- goto got_page;
- }
- }
- si->cluster_nr = SWAPFILE_CLUSTER;
-
- /* try to find an empty (even not aligned) cluster. */
- offset = si->lowest_bit;
- check_next_cluster:
- if (offset+SWAPFILE_CLUSTER-1 <= si->highest_bit)
- {
- unsigned long nr;
- for (nr = offset; nr < offset+SWAPFILE_CLUSTER; nr++)
- if (si->swap_map[nr])
- {
- offset = nr+1;
- goto check_next_cluster;
+ last_in_cluster = offset + SWAPFILE_CLUSTER;
+ else if (offset == last_in_cluster) {
+ spin_lock(&swap_lock);
+ si->cluster_next = offset-SWAPFILE_CLUSTER-1;
+ goto cluster;
}
- /* We found a completly empty cluster, so start
- * using it.
- */
- goto got_page;
+ if (unlikely(--latency_ration < 0)) {
+ cond_resched();
+ latency_ration = LATENCY_LIMIT;
+ }
+ }
+ spin_lock(&swap_lock);
+ goto lowest;
}
- /* No luck, so now go finegrined as usual. -Andrea */
- for (offset = si->lowest_bit; offset <= si->highest_bit ; offset++) {
- if (si->swap_map[offset])
- continue;
- si->lowest_bit = offset+1;
- got_page:
+
+ si->cluster_nr--;
+cluster:
+ offset = si->cluster_next;
+ if (offset > si->highest_bit)
+lowest: offset = si->lowest_bit;
+checks: if (!(si->flags & SWP_WRITEOK))
+ goto no_page;
+ if (!si->highest_bit)
+ goto no_page;
+ if (!si->swap_map[offset]) {
if (offset == si->lowest_bit)
si->lowest_bit++;
if (offset == si->highest_bit)
si->highest_bit--;
- if (si->lowest_bit > si->highest_bit) {
+ si->inuse_pages++;
+ if (si->inuse_pages == si->pages) {
si->lowest_bit = si->max;
si->highest_bit = 0;
}
si->swap_map[offset] = 1;
- si->inuse_pages++;
- si->cluster_next = offset+1;
+ si->cluster_next = offset + 1;
+ si->flags -= SWP_SCANNING;
return offset;
}
- si->lowest_bit = si->max;
- si->highest_bit = 0;
+
+ spin_unlock(&swap_lock);
+ while (++offset <= si->highest_bit) {
+ if (!si->swap_map[offset]) {
+ spin_lock(&swap_lock);
+ goto checks;
+ }
+ if (unlikely(--latency_ration < 0)) {
+ cond_resched();
+ latency_ration = LATENCY_LIMIT;
+ }
+ }
+ spin_lock(&swap_lock);
+ goto lowest;
+
+no_page:
+ si->flags -= SWP_SCANNING;
return 0;
}
int type, next;
int wrapped = 0;
- swap_list_lock();
+ spin_lock(&swap_lock);
if (nr_swap_pages <= 0)
goto noswap;
nr_swap_pages--;
continue;
swap_list.next = next;
- swap_device_lock(si);
- swap_list_unlock();
offset = scan_swap_map(si);
- swap_device_unlock(si);
- if (offset)
+ if (offset) {
+ spin_unlock(&swap_lock);
return swp_entry(type, offset);
- swap_list_lock();
+ }
next = swap_list.next;
}
nr_swap_pages++;
noswap:
- swap_list_unlock();
+ spin_unlock(&swap_lock);
return (swp_entry_t) {0};
}
goto bad_offset;
if (!p->swap_map[offset])
goto bad_free;
- swap_list_lock();
- swap_device_lock(p);
+ spin_lock(&swap_lock);
return p;
bad_free:
return NULL;
}
-static void swap_info_put(struct swap_info_struct * p)
-{
- swap_device_unlock(p);
- swap_list_unlock();
-}
-
static int swap_entry_free(struct swap_info_struct *p, unsigned long offset)
{
int count = p->swap_map[offset];
p = swap_info_get(entry);
if (p) {
swap_entry_free(p, swp_offset(entry));
- swap_info_put(p);
+ spin_unlock(&swap_lock);
}
}
struct swap_info_struct *p;
swp_entry_t entry;
- entry.val = page->private;
+ entry.val = page_private(page);
p = swap_info_get(entry);
if (p) {
/* Subtract the 1 for the swap cache itself */
count = p->swap_map[swp_offset(entry)] - 1;
- swap_info_put(p);
+ spin_unlock(&swap_lock);
}
return count;
}
if (page_count(page) != 2) /* 2: us + cache */
return 0;
- entry.val = page->private;
+ entry.val = page_private(page);
p = swap_info_get(entry);
if (!p)
return 0;
}
write_unlock_irq(&swapper_space.tree_lock);
}
- swap_info_put(p);
+ spin_unlock(&swap_lock);
if (retval) {
swap_free(entry);
if (p) {
if (swap_entry_free(p, swp_offset(entry)) == 1)
page = find_trylock_page(&swapper_space, entry.val);
- swap_info_put(p);
+ spin_unlock(&swap_lock);
}
if (page) {
int one_user;
}
/*
- * Always set the resulting pte to be nowrite (the same as COW pages
- * after one process has exited). We don't know just how many PTEs will
- * share this swap entry, so be cautious and let do_wp_page work out
- * what to do if a write is requested later.
- *
- * vma->vm_mm->page_table_lock is held.
+ * No need to decide whether this PTE shares the swap entry with others,
+ * just let do_wp_page work it out if a write is requested later - to
+ * force COW, vm_page_prot omits write permission from any private vma.
*/
static void unuse_pte(struct vm_area_struct *vma, pte_t *pte,
unsigned long addr, swp_entry_t entry, struct page *page)
{
- inc_mm_counter(vma->vm_mm, rss);
+ inc_mm_counter(vma->vm_mm, anon_rss);
get_page(page);
set_pte_at(vma->vm_mm, addr, pte,
pte_mkold(mk_pte(page, vma->vm_page_prot)));
unsigned long addr, unsigned long end,
swp_entry_t entry, struct page *page)
{
- pte_t *pte;
pte_t swp_pte = swp_entry_to_pte(entry);
+ pte_t *pte;
+ spinlock_t *ptl;
+ int found = 0;
- pte = pte_offset_map(pmd, addr);
+ pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
do {
/*
* swapoff spends a _lot_ of time in this loop!
* Test inline before going to call unuse_pte.
*/
if (unlikely(pte_same(*pte, swp_pte))) {
- unuse_pte(vma, pte, addr, entry, page);
- pte_unmap(pte);
- return 1;
+ unuse_pte(vma, pte++, addr, entry, page);
+ found = 1;
+ break;
}
} while (pte++, addr += PAGE_SIZE, addr != end);
- pte_unmap(pte - 1);
- return 0;
+ pte_unmap_unlock(pte - 1, ptl);
+ return found;
}
static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud,
down_read(&mm->mmap_sem);
lock_page(page);
}
- spin_lock(&mm->page_table_lock);
for (vma = mm->mmap; vma; vma = vma->vm_next) {
if (vma->anon_vma && unuse_vma(vma, entry, page))
break;
}
- spin_unlock(&mm->page_table_lock);
up_read(&mm->mmap_sem);
/*
* Currently unuse_mm cannot fail, but leave error handling
int count;
/*
- * No need for swap_device_lock(si) here: we're just looking
+ * No need for swap_lock here: we're just looking
* for whether an entry is in use, not modifying it; false
* hits are okay, and sys_swapoff() has already prevented new
- * allocations from this area (while holding swap_list_lock()).
+ * allocations from this area (while holding swap_lock).
*/
for (;;) {
if (++i >= max) {
* report them; but do report if we reset SWAP_MAP_MAX.
*/
if (*swap_map == SWAP_MAP_MAX) {
- swap_device_lock(si);
+ spin_lock(&swap_lock);
*swap_map = 1;
- swap_device_unlock(si);
+ spin_unlock(&swap_lock);
reset_overflow = 1;
}
}
/*
- * After a successful try_to_unuse, if no swap is now in use, we know we
- * can empty the mmlist. swap_list_lock must be held on entry and exit.
- * Note that mmlist_lock nests inside swap_list_lock, and an mm must be
+ * After a successful try_to_unuse, if no swap is now in use, we know
+ * we can empty the mmlist. swap_lock must be held on entry and exit.
+ * Note that mmlist_lock nests inside swap_lock, and an mm must be
* added to the mmlist just after page_duplicate - before would be racy.
*/
static void drain_mmlist(void)
BUG_ON(!PageLocked(page)); /* It pins the swap_info_struct */
if (PageSwapCache(page)) {
- swp_entry_t entry = { .val = page->private };
+ swp_entry_t entry = { .val = page_private(page) };
struct swap_info_struct *sis;
sis = get_swap_info_struct(swp_type(entry));
mapping = victim->f_mapping;
prev = -1;
- swap_list_lock();
+ spin_lock(&swap_lock);
for (type = swap_list.head; type >= 0; type = swap_info[type].next) {
p = swap_info + type;
if ((p->flags & SWP_ACTIVE) == SWP_ACTIVE) {
}
if (type < 0) {
err = -EINVAL;
- swap_list_unlock();
+ spin_unlock(&swap_lock);
goto out_dput;
}
if (!security_vm_enough_memory(p->pages))
vm_unacct_memory(p->pages);
else {
err = -ENOMEM;
- swap_list_unlock();
+ spin_unlock(&swap_lock);
goto out_dput;
}
if (prev < 0) {
}
nr_swap_pages -= p->pages;
total_swap_pages -= p->pages;
- swap_device_lock(p);
p->flags &= ~SWP_WRITEOK;
- swap_device_unlock(p);
- swap_list_unlock();
+ spin_unlock(&swap_lock);
current->flags |= PF_SWAPOFF;
err = try_to_unuse(type);
current->flags &= ~PF_SWAPOFF;
- /* wait for any unplug function to finish */
- down_write(&swap_unplug_sem);
- up_write(&swap_unplug_sem);
-
if (err) {
/* re-insert swap space back into swap_list */
- swap_list_lock();
+ spin_lock(&swap_lock);
for (prev = -1, i = swap_list.head; i >= 0; prev = i, i = swap_info[i].next)
if (p->prio >= swap_info[i].prio)
break;
nr_swap_pages += p->pages;
total_swap_pages += p->pages;
p->flags |= SWP_WRITEOK;
- swap_list_unlock();
+ spin_unlock(&swap_lock);
goto out_dput;
}
+
+ /* wait for any unplug function to finish */
+ down_write(&swap_unplug_sem);
+ up_write(&swap_unplug_sem);
+
destroy_swap_extents(p);
down(&swapon_sem);
- swap_list_lock();
+ spin_lock(&swap_lock);
drain_mmlist();
- swap_device_lock(p);
+
+ /* wait for anyone still in scan_swap_map */
+ p->highest_bit = 0; /* cuts scans short */
+ while (p->flags >= SWP_SCANNING) {
+ spin_unlock(&swap_lock);
+ schedule_timeout_uninterruptible(1);
+ spin_lock(&swap_lock);
+ }
+
swap_file = p->swap_file;
p->swap_file = NULL;
p->max = 0;
swap_map = p->swap_map;
p->swap_map = NULL;
p->flags = 0;
- swap_device_unlock(p);
- swap_list_unlock();
+ spin_unlock(&swap_lock);
up(&swapon_sem);
vfree(swap_map);
inode = mapping->host;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- swap_list_lock();
+ spin_lock(&swap_lock);
p = swap_info;
for (type = 0 ; type < nr_swapfiles ; type++,p++)
if (!(p->flags & SWP_USED))
* swp_entry_t or the architecture definition of a swap pte.
*/
if (type > swp_type(pte_to_swp_entry(swp_entry_to_pte(swp_entry(~0UL,0))))) {
- swap_list_unlock();
+ spin_unlock(&swap_lock);
goto out;
}
if (type >= nr_swapfiles)
p->highest_bit = 0;
p->cluster_nr = 0;
p->inuse_pages = 0;
- spin_lock_init(&p->sdev_lock);
p->next = -1;
if (swap_flags & SWAP_FLAG_PREFER) {
p->prio =
} else {
p->prio = --least_priority;
}
- swap_list_unlock();
+ spin_unlock(&swap_lock);
name = getname(specialfile);
error = PTR_ERR(name);
if (IS_ERR(name)) {
error = bd_claim(bdev, sys_swapon);
if (error < 0) {
bdev = NULL;
+ error = -EINVAL;
goto bad_swap;
}
p->old_block_size = block_size(bdev);
}
p->lowest_bit = 1;
+ p->cluster_next = 1;
+
/*
* Find out how many pages are allowed for a single swap
* device. There are two limiting factors: 1) the number of
}
down(&swapon_sem);
- swap_list_lock();
- swap_device_lock(p);
+ spin_lock(&swap_lock);
p->flags = SWP_ACTIVE;
nr_swap_pages += nr_good_pages;
total_swap_pages += nr_good_pages;
} else {
swap_info[prev].next = p - swap_info;
}
- swap_device_unlock(p);
- swap_list_unlock();
+ spin_unlock(&swap_lock);
up(&swapon_sem);
error = 0;
goto out;
}
destroy_swap_extents(p);
bad_swap_2:
- swap_list_lock();
+ spin_lock(&swap_lock);
swap_map = p->swap_map;
p->swap_file = NULL;
p->swap_map = NULL;
p->flags = 0;
if (!(swap_flags & SWAP_FLAG_PREFER))
++least_priority;
- swap_list_unlock();
+ spin_unlock(&swap_lock);
vfree(swap_map);
if (swap_file)
filp_close(swap_file, NULL);
unsigned int i;
unsigned long nr_to_be_unused = 0;
- swap_list_lock();
+ spin_lock(&swap_lock);
for (i = 0; i < nr_swapfiles; i++) {
if (!(swap_info[i].flags & SWP_USED) ||
(swap_info[i].flags & SWP_WRITEOK))
}
val->freeswap = nr_swap_pages + nr_to_be_unused;
val->totalswap = total_swap_pages + nr_to_be_unused;
- swap_list_unlock();
+ spin_unlock(&swap_lock);
}
/*
p = type + swap_info;
offset = swp_offset(entry);
- swap_device_lock(p);
+ spin_lock(&swap_lock);
if (offset < p->max && p->swap_map[offset]) {
if (p->swap_map[offset] < SWAP_MAP_MAX - 1) {
p->swap_map[offset]++;
result = 1;
}
}
- swap_device_unlock(p);
+ spin_unlock(&swap_lock);
out:
return result;
}
/*
- * swap_device_lock prevents swap_map being freed. Don't grab an extra
+ * swap_lock prevents swap_map being freed. Don't grab an extra
* reference on the swaphandle, it doesn't matter if it becomes unused.
*/
int valid_swaphandles(swp_entry_t entry, unsigned long *offset)
toff++, i--;
*offset = toff;
- swap_device_lock(swapdev);
+ spin_lock(&swap_lock);
do {
/* Don't read-ahead past the end of the swap area */
if (toff >= swapdev->max)
toff++;
ret++;
} while (--i);
- swap_device_unlock(swapdev);
+ spin_unlock(&swap_lock);
return ret;
}